In 2011, AIS recognized a shift in customer needs towards more advanced cloud computing solutions. The primary challenges faced by AIS were the need for higher speed to interface compute hosts with storage and the increased complexity of network management tasks. To address these challenges, AIS needed to move to 10 Gigabit Ethernet (10GbE) with a higher port density. During the vendor selection phase, AIS discovered that some of their customers were already using Arista Networks products in their colocation space. This, along with insights from IT professionals involved in VMware deployments, led AIS to consider Arista Networks for their cloud computing infrastructure.

The Polish National Centre for Nuclear Research and its Świerk Computing Centre needed to improve its core network infrastructure to facilitate the upgrade of its supercomputing resources and provide a more efficient foundation for further growth. The centre was continually looking at technologies to help it harness its vast computing capability and mitigate any technical hurdles to help it deliver its world-class research capabilities. Although currently undergoing a validation process, the installation is likely to be categorized as one of the top 500 most powerful supercomputers in the world and certainly in the top 3 in Poland. The strategic goal is to build a unique science and technology competence centre to support the development of the Polish energy sector and all related fields of science. To meet this aim, an architecture refresh would be required to allow the cluster to scale as needed, but with particular care to avoid any bottlenecks that could impact future performance. One such area of particular concern was the core networking technology that would underpin the centre for the next decade of expansion.

Cyso needed to build a cost-effective cloud platform using OpenStack and required a scalable and high-performance switching architecture to meet its business aims. The company faced the challenge of delivering a public cloud service that could meet critical cost considerations without sacrificing reliability and features. Additionally, the choice of switching architecture was crucial to meet the performance demands of its cloud and enable automation features vital for its self-service ethos. Cyso also needed a robust networking layer to analyze anomalies and act accordingly, especially given the security risks associated with open platforms like OpenStack.

The European Centre for Medium-Range Weather Forecasts (ECMWF) needed to ensure its network layer was not a bottleneck for advanced research and weather prediction on upgraded supercomputer clusters. The supercomputer generates a huge amount of data which needs to be offloaded to storage and post-processing as quickly as possible. The network cannot be a bottleneck for this process, and it must cope with predicted upgrades or new workloads. In 2010, with the Centre’s existing IBM-based supercomputers due for upgrade, the team began looking at a possible replacement for its current Force 10 based network.

Sky Italia needed a large-scale routing system within its Milan facility to deliver mission critical SDI over IP network infrastructure. Sky Italia supports more than 150 of its own channels and following a reorganisation, the Italian operation would also handle all signal contribution for Sky Deutschland from operations centres in Milan and Rome. Sky Italia already transports individual feeds and multiplexed streams between the two locations but faced with the burden of handling signal contribution between Milan and Munich, Sky Italia needed to migrate to a large-scale routing system distributed across several floors within the Milan facility. To meet the future evolution towards an all IP based production and broadcast environment including IP-based disaster recovery, Sky Italia decided to design the system around an IP switching core using high capacity data centre switches. However, the new IP environment also needed to connect to legacy SDI systems within the Milan facility. The ultimate goal was to leverage the speed and scalability benefits of IP, while achieving the same level of switching quality as a traditional baseband router.

Schuberg Philis needed a flexible switching architecture to support its 'Cloud Pods' and create a mission-critical cloud for its customers. The company operates under a 100% principle, ensuring product quality, customer satisfaction, and openness. With nearly 500 customers, including major banks and supermarket chains, Schuberg Philis required a robust infrastructure to meet the high demands of its clients. In 2011, as cloud computing was gaining traction, Schuberg Philis recognized the need for agility and flexibility offered by cloud solutions. However, their customers were conservative and hesitant about public cloud adoption. Therefore, Schuberg Philis embarked on a project to build its own Mission Critical Cloud, setting stringent security and performance criteria to meet their high standards.

Following the UK's agreement in 1996 to sign the Comprehensive Nuclear Test-Ban Treaty, AWE's work must be completed without actual test firing of weapons. This poses enormous technical and engineering challenges, necessitating high performance computing (HPC) systems for simulation, modeling, design, plasma physics, materials science, and hydrodynamics. AWE has invested significantly in its HPC capability, operating several supercomputing platforms. The demands on networking are significant, requiring cutting-edge technology to manage the high volume of calculations and data generated.

The latest development is Multiplay’s hybrid cloud orchestration platform that helps publishers to cost effectively provision and scale multiplayer environments to meet peaks and troughs in demand while delivering the best possible gamer experience. As Tom Penrose, team lead for systems at Multiplay says, “Spending £50 on a brand new game and not being able to get online is just an awful experience for players and publishers are recognising that this type of situation is going to damage their brands.”\n\n“However, setting up and running potentially hundreds of game servers so that everything is in place on game launch day is a major CAPEX expenditure and risk, It’s sometimes hard to gauge demand for a new title and where it’s going to be coming from across the globe” says Penrose, “Games also evolve with new patches and mods that push and pull player numbers – even time of day is a critical factor.”\n\nAs a company that has spent 20 years working in the area of multiplayer infrastructure, Multiplay has built a number of tools to help provision and manage servers; both for itself and third party customers. The culmination of its development work is its hybrid cloud orchestration platform. The system is used to provision game servers across either its estate of bare metal servers co-located at data centres across the world or to spin up virtual servers in private clouds. The system is highly automated and dynamic allowing servers to be brought online during periods of demand and then released back into the pool as demand ebbs.

Leonix faced significant challenges with data replication between sites due to its old legacy network switches and storage equipment. The existing infrastructure exhibited unacceptable levels of latency and throughput constraints, which became problematic as traffic volumes and the number of virtual machines grew. With an expected annual growth of around 30%, Leonix needed a new network and storage architecture to ensure service availability and scalability. The company approached several solution providers and technology vendors to find a reliable and scalable solution that could grow with their business.

VanEck 是一家以其创新金融解决方案而闻名的资产管理公司，正在寻求将其业务扩展到国际市场。该公司的理念是为投资者提供增强其投资组合的机会，这使他们成为首批为客户提供进入国际市场的资产管理公司之一。然而，挑战在于与当地投资者就全球增长机会进行有效沟通。该公司需要将其网站内容、监管文件和营销材料翻译成多种语言，以满足不同地区的需求。此外，快速增长的交易所交易基金 (ETF) 和交易所交易票据 (ETN) 市场给向广大受众营销这些产品带来了挑战。该公司还面临着保持平衡沟通的挑战，强调其产品的优势和风险。